Fabrizio Russo

Dr. Fabrizio Russo is a Research Associate in the Computational Logic and Argumentation group within the Department of Computing at Imperial College London's Faculty of Engineering. He obtained his PhD in Safe and Trusted AI from Imperial College in 2025, funded by the UKRI Centre for Doctoral Training (STAI). Previously, he spent six years in industry as Head of Data Science at 4most Europe, specializing in credit risk modeling.

His research focuses on augmenting human decision-making through Causal Discovery, Computational Argumentation, and Explainable AI. He develops transparent techniques that integrate causality with machine learning to create contestable AI systems for high-stakes domains. Key interests include human-AI debate frameworks, knowledge injection in neural networks, and Shapley-based causal structure learning.

Publications demonstrate sustained contributions to knowledge-driven AI, with recent works exploring argumentative causal discovery (2024), contestable neural networks (2023), and classifier explanation methods (2023). Research consistently combines formal reasoning with practical applications in trustworthy AI.

Awards & Recognition:

• AISTATS 2023 Top-Reviewer Award

Teaching & Service: Served as Graduate Teaching Assistant for Introduction to Machine Learning (2021-2022). Co-organizes the Explainable AI Seminars @ Imperial and contributes as reviewer for top conferences (ICLR, NeurIPS, ICML). Assistant Chair for XAI-FIN workshops at ICAIF (2022-2024).